DSTC8-AVSD: Multimodal Semantic Transformer Network with Retrieval Style Word Generator

Audio Visual Scene-aware Dialog (AVSD) is the task of generating a response for a question with a given scene, video, audio, and the history of previous turns in the dialog. Existing systems for this task employ the transformers or recurrent neural network-based architecture with the encoder-decoder...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2020-04
Main Authors: Lee, Hwanhee, Yoon, Seunghyun, Dernoncourt, Franck, Kim, Doo Soon, Bui, Trung, Jung, Kyomin
Format: Article
Language:English
Subjects:
Coders
Encoders-Decoders
Recurrent neural networks
Semantics
Words (language)
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Audio Visual Scene-aware Dialog (AVSD) is the task of generating a response for a question with a given scene, video, audio, and the history of previous turns in the dialog. Existing systems for this task employ the transformers or recurrent neural network-based architecture with the encoder-decoder framework. Even though these techniques show superior performance for this task, they have significant limitations: the model easily overfits only to memorize the grammatical patterns; the model follows the prior distribution of the vocabularies in a dataset. To alleviate the problems, we propose a Multimodal Semantic Transformer Network. It employs a transformer-based architecture with an attention-based word embedding layer that generates words by querying word embeddings. With this design, our model keeps considering the meaning of the words at the generation stage. The empirical results demonstrate the superiority of our proposed model that outperforms most of the previous works for the AVSD task.
ISSN:2331-8422